Contributo in atti di convegno, 2017, ENG, 10.1109/OCEANSE.2017.8084721

Machine learning methods for acoustic-based automatic Posidonia meadows detection by means of unmanned marine vehicles

Ferretti Roberta, Bibuli Marco, Caccia Massimo, Chiarella Davide, Odetti Angelo, Ranieri Andrea, Zereik Enrica and Bruzzone Gabriele

Consiglio Nazionale delle Ricerche - Istituto di Studi sui Sistemi Intelligenti per l'Automazione Via De Marini 6 - 16149, Genova, Italy

This work describes the exploitation of a Remotely Operated Vehicle (ROV), equipped with a multi-parametric sensors package (acoustic and video), for the exploration and characterisation of sea-bottoms covered with Posidonia oceanica seagrass, which represents a valuable indicator of the environmental health. The data collection is achieved by the employment of a single beam echosounder and a down-looking underwater camera. An acoustic data procedural analysis based on machine learning methods was developed to automatically detect the Posidonia presence, so that in future works it will be possible to operate also in low-visibility conditions, using only the acoustic sensors. Data acquisition was carried out over different seafloor types in coastal area near Biograd Na Moru (Croatia) and the preliminary results are reported in the paper.

OCEANS 2017 - Aberdeen, pp. 1–6, Aberdeen, UK, 19-22/6/2017

Keywords

Machine Learning, Posidonia Detection, unmanned marine vehicles

CNR authors

Chiarella Davide, Odetti Angelo, Ferretti Roberta, Caccia Massimo, Bruzzone Gabriele, Bibuli Marco, Zereik Enrica, Ranieri Andrea

CNR institutes

ILC – Istituto di linguistica computazionale "Antonio Zampolli", IMATI – Istituto di matematica applicata e tecnologie informatiche "Enrico Magenes", INM – Istituto di iNgegneria del Mare

ID: 378509

Year: 2017

Type: Contributo in atti di convegno

Creation: 2017-11-21 15:24:57.000

Last update: 2022-02-25 15:02:57.000

External IDs

CNR OAI-PMH: oai:it.cnr:prodotti:378509

DOI: 10.1109/OCEANSE.2017.8084721

Scopus: 2-s2.0-85044633776

ISI Web of Science (WOS): 000426997000152